© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14594
    Prev
    Next
    INDEX
    Explanations

    instances of the word "das"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "repeated" in code

    np_acts-logits-general · gemini-2.0-flash

    specialist or specialized concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.87
    webElement
    -0.79
     ISNI
    -0.76
    Autoritní
    -0.74
    twimg
    -0.70
    SequentialGroup
    -0.70
    ContentAlignment
    -0.68
    IVEREF
    -0.67
    CopyWith
    -0.67
    IsMutable
    -0.67
    POSITIVE LOGITS
    Protos
    0.59
    weakSelf
    0.47
     Specialties
    0.46
     Specialized
    0.46
    مصادر
    0.45
     Specialist
    0.45
    specialized
    0.45
     specialist
    0.44
     specialists
    0.44
     specialized
    0.43
    Activations Density 0.086%

    No Known Activations